Modelpublic

eternalis/Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face

1likes439downloads

Model Card

Qwen3.8-27B-OBLITERATED-V3-Sharp-oQ4e-mtp

MLX oQ4e quantization of [OBLITERATUS/Qwen3.8-27B-OBLITERATED](https://huggingface.co/OBLITERATUS/Qwen3.8-27B-OBLITERATED) (V3 – Deep Liberation).

Quantized with oMLX v0.6.3rc3.

The model includes the MTP (Multi-Token Prediction) weights for speculative decoding with compatible runtimes.

The original vision components have been removed to reduce memory usage. This release is therefore text-only.

It also includes the [Qwen Sharp Chat Template](https://huggingface.co/peculiar-ragdoll/Qwen-Sharp-Chat-Templates), optimized for more concise and token-efficient Qwen 3.8 responses.

Quantization details

—Base model: OBLITERATUS/Qwen3.8-27B-OBLITERATED (V3)
—Original base: Qwen/Qwen3.8-27B
—Quantization: oQ4e
—Quantizer: oMLX 0.6.3rc3
—Format: MLX Safetensors
—MTP: Included
—Vision: Removed
—Chat template: Qwen Sharp